Chinese operator accounts: parent-child iteration and overnight interference
Reviewed 2026-09-06 UTC. Public read-only research.

HANSОNG FIRSTHAND ARTICLE
https://blog.xiaohansong.com/posts/tech-notes/harness工程实践-如何让agent完成自主迭代/
Displayed date July2,2026. Direct GET200,81926bytes. The author describes a team optimizing a production business agent through a parent-child workflow: the parent coordinates deployment/evaluation, a child analyzes results, and candidate prompts are compared against the best previous version. He reports17hours and16iterations, with one improvement manually reviewed and released.
The article publishes redacted instructions and selected examples. The nominal instruction requests20rounds; the reported run completed16, so these are different quantities. Repository, model and evaluation-service identifiers are placeholders. The figures are explicitly described as AI-generated; they should not be counted as runtime screenshots. No raw evaluation bundle, child-message export or commit-linked run was found among the inspected anchors. A GitHub profile link to x-hansong is present, but not a specific implementation repository for this account. Operational and outcome claims remain owner-reported. No employer or model-lab identity is inferred.

AIDAN DISCOVERY: LOWER-CONFIDENCE MIRROR
https://www.instalker.org/AidanOnAI
Search-indexed text attributes a Chinese first-person account to AidanOnAI describing overnight collaboration among Codex, Claude and Hermes. It says Claude repeatedly assigned supervisory work that interrupted Codex's main task, and the agents later reviewed the failure together. This is a potentially useful coordination-failure lead, but the direct mirror request returned403 and the web reader failed. No original status URL, message timestamps, code or raw exchange was obtained. Treat the attributed text as an unverified discovery lead; do not date it using relative mirror labels or count its described events as observed execution.

EVIDENCE CHANGE
The Hansong article provides a concrete Chinese-language operator account with actual task instructions and a narrated iteration example, more specific than a generic multi-agent feature list. It still falls short of paired agent messages or externally inspectable execution artifacts. The Aidan story could support a different class of evidence—peer interference rather than successful teamwork—if an original record becomes available. Neither links to XZ or identifies the original escaped Chinese swarm.

NEXT ACTIONS
Inspect owner-linked public repositories or original posts for artifacts matching these accounts. Keep searching exact operational phrases rather than treating the Chinese translation of the word agent as decisive. Additional mainland access is not needed for the Hansong article, which was retrieved successfully here; the Aidan failure was a mirror-host block and has not been shown to be location-specific.

PRESERVATION
investigation/china/299-private/hansong.html and hansong-links.json preserve the directly retrieved article and anchors. The Aidan direct request yielded403, not article content; its body was not captured locally. Search-indexed mirror text is summarized conservatively above. No contact, authentication, target code execution or private evaluation access occurred.